A complete hand-drawn sketch vectorization framework

Donati, Luca Luparia; Cesano, Simone; Prati, Andrea

doi:10.1007/s11042-019-7311-3

Cited by 21 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous later works have been proposed following this same basic cluster-and-replace framework for vector graphics [Liu et al 2018[Liu et al , 2015Ogawa et al 2016;Orbay and Kara 2011;Shesh and Chen 2008]. Another line of work simultaneously vectorizes and simplifies a raster image of a sketch [Bessmeltsev and Solomon 2019;Donati et al 2019;Favreau et al 2016;Kim et al 2018;Noris et al 2013;Parakkat et al 2018]. This is a more challenging problem, as parametric data is unavailable for the input curves.…”

Section: Related Workmentioning

confidence: 99%

A benchmark for rough sketch cleanup

2020

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

A benchmark for rough sketch cleanup

2020

View full text Add to dashboard Cite

show abstract

“…Vectorization algorithms for clean line drawings typically rely on 1-skeleton or raw image gradient to extract curve directions, endpoints, junctions, and connectivity [Bo et al 2016;Donati et al 2017Donati et al , 2019Najgebauer and Scherer 2019;Noris et al 2013]. Noris et al [2013] vectorize clean digital line drawings via a global approach to topology.…”

Section: Input Bitmapmentioning

confidence: 99%

Keypoint-driven line drawing vectorization via PolyVector flow

et al. 2021

View full text Add to dashboard Cite

Line drawing vectorization is a daily task in graphic design, computer animation, and engineering, necessary to convert raster images to a set of curves for editing and geometry processing. Despite recent progress in the area, automatic vectorization tools often produce spurious branches or incorrect connectivity around curve junctions; or smooth out sharp corners. These issues detract from the use of such vectorization tools, both from an aesthetic viewpoint and for feasibility of downstream applications (e.g., automatic coloring or inbetweening). We address these problems by introducing a novel line drawing vectorization algorithm that splits the task into three components: (1) finding keypoints, i.e., curve endpoints, junctions, and sharp corners; (2) extracting drawing topology, i.e., finding connections between keypoints; and (3) computing the geometry of those connections. We compute the optimal geometry of the connecting curves via a novel geometric flow --- PolyVector Flow --- that aligns the curves to the drawing, disambiguating directions around Y-, X-, and T-junctions. We show that our system robustly infers both the geometry and topology of detailed complex drawings. We validate our system both quantitatively and qualitatively, demonstrating that our method visually outperforms previous work.

show abstract

“…Moreover, the handwriting pressure was divided into 4 levels, and the pressure level corresponding to a randomly selected frame was obtained using the constructed rounding function and normalized to satisfy the requirement of initial simplification. Donati et al [32] created a "simulated" dataset called an inverse dataset. The strokes pressure in this dataset was applied to the start and end portions of each trait (first-last VOLUME 9, 2021 10%), which was lower to satisfy the requirement of real traits and data lightweight.…”

Section: ) Simplify Trajectory Using Pressure Informationmentioning

confidence: 99%

A Lightweight Processing Method for Hand-Drawn Pressure-Sensitive Trajectories Oriented Toward Web-Based 3D Modeling

et al. 2021

View full text Add to dashboard Cite

Digital geometry processing of hand-drawn pressure-sensitive trajectories oriented toward Web-based three-dimensional (3D) modeling becomes attractive problem. Existing practices usually focus on converting raw trajectories into 3D stroke meshes with consistent line width, which the pressure information can not been fully utilized for denoising, simplification and reflecting realistic graphics of 3D stroke mesh. Also, there are little research on the high quality of trajectory with data transmission fluency and light weight in the Web environment. We propose a lightweight processing method for hand-drawn pressure-sensitive trajectories that is oriented toward Web-based 3D modeling. An angle-chord height united trajectory simplification (ACUTS) algorithm is proposed, in which the discrete points are simplified by comprehensively considering the angle deviation and chord height deviation with the sliding window mechanism. In addition, a lightweight reconstruction algorithm based on pressure -sensitivity for discrete points (LRPDP) is also proposed, in which the pressure value can be fully utilized for simplifying the redundant points while ensuring the reconstructed 3D stroke mesh more realistic. Besides, the experimental results show that compared to some other methods, we perform best in terms of data reduction using compression ratio and reduction percentages. We also perform best in terms of high accuracy of 3D stroke mesh using mean stochastic error distance, local maximum error and total length error. Although the insufficient utilization of the pressure-sensitive information limits our research to some extents, the significance of our research is to provide a new strategy to realize Web-based 3D modeling using hand drawing mode.

show abstract

A complete hand-drawn sketch vectorization framework

Cited by 21 publications

References 28 publications

A benchmark for rough sketch cleanup

A benchmark for rough sketch cleanup

Keypoint-driven line drawing vectorization via PolyVector flow

A Lightweight Processing Method for Hand-Drawn Pressure-Sensitive Trajectories Oriented Toward Web-Based 3D Modeling

Contact Info

Product

Resources

About